Examination of Deep Learning based NOMA System Considering Node Mobility and Imperfect CSI

Q3 Engineering Radioelectronics and Communications Systems Pub Date : 2024-08-07 DOI:10.3103/s0735272723070026

Manoj Kumar Beuria, Ravi Shankar, Indrajeet Kumar, Bhanu Pratap Chaudhary, V. Gokula Krishnan, Sudhansu Sekhar Singh

{"title":"Examination of Deep Learning based NOMA System Considering Node Mobility and Imperfect CSI","authors":"Manoj Kumar Beuria, Ravi Shankar, Indrajeet Kumar, Bhanu Pratap Chaudhary, V. Gokula Krishnan, Sudhansu Sekhar Singh","doi":"10.3103/s0735272723070026","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>This paper examines the efficiency of a downlink non-orthogonal multiple access (NOMA) system by using a deep learning (DL)-based stacked long short-term memory (S-LSTM) scheme. The vehicle-to-vehicle (V2V) channel is considered to be time-selective as a result of node mobility and the presence of imprecise channel state information (CSI). The use of the fifth generation (5G) tapped delay line type C (TDL-C) independent and identically distributed (IID) fading channel models allows for the production of channel taps that properly replicate the Nakagami-m fading wireless channel. The paper examines the outage probability (OP) and symbol error rate (SER) of both traditional and suggested channel estimators. It analyzes these metrics under various fading parameters, pilot symbols (PS), learning rate (LR), and batch size. The training of deep neural network (DNN) models is performed using the Adam optimizer. Enhancing the signal-to-noise ratio (SNR) may decrease the SER which results in the enhanced identification of the downlink channel in NOMA cell-based systems. Reducing the LR has a positive effect on the SER, validating the analytical findings that indicate greater changes in DNN weights and larger validation mistakes when the LR is raised. Nevertheless, this benefit is accompanied by the drawback of more frequent updates, resulting in a delay in the model’s convergence.</p>","PeriodicalId":52470,"journal":{"name":"Radioelectronics and Communications Systems","volume":"22 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radioelectronics and Communications Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3103/s0735272723070026","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 0

Abstract

This paper examines the efficiency of a downlink non-orthogonal multiple access (NOMA) system by using a deep learning (DL)-based stacked long short-term memory (S-LSTM) scheme. The vehicle-to-vehicle (V2V) channel is considered to be time-selective as a result of node mobility and the presence of imprecise channel state information (CSI). The use of the fifth generation (5G) tapped delay line type C (TDL-C) independent and identically distributed (IID) fading channel models allows for the production of channel taps that properly replicate the Nakagami-m fading wireless channel. The paper examines the outage probability (OP) and symbol error rate (SER) of both traditional and suggested channel estimators. It analyzes these metrics under various fading parameters, pilot symbols (PS), learning rate (LR), and batch size. The training of deep neural network (DNN) models is performed using the Adam optimizer. Enhancing the signal-to-noise ratio (SNR) may decrease the SER which results in the enhanced identification of the downlink channel in NOMA cell-based systems. Reducing the LR has a positive effect on the SER, validating the analytical findings that indicate greater changes in DNN weights and larger validation mistakes when the LR is raised. Nevertheless, this benefit is accompanied by the drawback of more frequent updates, resulting in a delay in the model’s convergence.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

考虑节点移动性和不完美 CSI 的基于深度学习的 NOMA 系统研究

摘要本文通过使用基于深度学习（DL）的堆叠长短期记忆（S-LSTM）方案，研究了下行非正交多址（NOMA）系统的效率。由于节点的移动性和不精确信道状态信息（CSI）的存在，车对车（V2V）信道被认为具有时间选择性。使用第五代（5G）C 型分接延迟线（TDL-C）独立且同分布（IID）衰落信道模型，可以产生适当复制 Nakagami-m 衰减无线信道的信道分接。本文研究了传统和建议信道估计器的中断概率 (OP) 和符号错误率 (SER)。它分析了这些指标在不同衰减参数、先导符号（PS）、学习率（LR）和批量大小下的情况。使用 Adam 优化器对深度神经网络（DNN）模型进行训练。提高信噪比（SNR）可降低 SER，从而增强基于 NOMA 小区系统的下行链路信道识别能力。降低信噪比对 SER 有积极影响，这验证了分析结果，即提高信噪比时 DNN 权重变化更大，验证错误也更大。然而，这种好处也伴随着更新更频繁的缺点，导致模型收敛延迟。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Radioelectronics and Communications Systems Engineering-Electrical and Electronic Engineering

CiteScore

2.10

自引率

0.00%

发文量

期刊介绍： Radioelectronics and Communications Systems covers urgent theoretical problems of radio-engineering; results of research efforts, leading experience, which determines directions and development of scientific research in radio engineering and radio electronics; publishes materials of scientific conferences and meetings; information on scientific work in higher educational institutions; newsreel and bibliographic materials. Journal publishes articles in the following sections:Antenna-feeding and microwave devices;Vacuum and gas-discharge devices;Solid-state electronics and integral circuit engineering;Optical radar, communication and information processing systems;Use of computers for research and design of radio-electronic devices and systems;Quantum electronic devices;Design of radio-electronic devices;Radar and radio navigation;Radio engineering devices and systems;Radio engineering theory;Medical radioelectronics.